Pseudo-rigid body models tested on real blueberry plants in field
How Well Do Pseudo-Rigid Body Models Capture Real Plants? In-Field Validation of Simulated Blueberry Canes
Robotics
Summary
Tasks like pruning blueberry plants require robots to touch and bend the plants carefully. To help robots understand how plants bend, people use computer models made of linked rigid beams that act like springs. This paper checks how well these models match the actual bending of blueberry canes by comparing computer simulations with real measurements taken on a farm. The researchers found the model’s accuracy is very sensitive to how plant thickness and flexibility are estimated, which can change with the season and plant variety.
What this means in practice
- •For agricultural robotics teams: Improve simulation models robots use to physically interact with fruit plants like blueberries for tasks such as pruning and harvesting.
- •For agricultural equipment designers: Use validated plant models to design better robotic tools that account for the real mechanical behavior of blueberry canes.
Authors
Hannah Kolano, Chelse VanAtter, Wei Yang, Cindy Grimm, Joseph R. Davidson
Abstract
Many labor-intensive tasks in fruit production such as pruning require physically interacting with the plant (e.g., pushing, pulling, bending limbs, etc.). Due to increasing labor shortages, there is widespread interest in the adoption of robotics in this area. When the robot must physically interact with the system, a deformable model of the plant is beneficial. Coupled, spring-loaded beams have been used in prior work to build deformable plant models in simulation for learning, planning, and control, but this approach has rarely been validated against the mechanical properties of real-world plants. In this paper, we use this rigid-body model, grounded in real material properties and beam bending theory, to simulate the deformation of blueberry canes under loading. To validate the model, we simulate the canes in MuJoCo and compare their behavior with real-world data collected from probing canes at a commercial farm with a custom testbed. We perform sensitivity analysis on several key modeling variables and show that this approach is highly sensitive to the plant diameter calculations and a priori flexural modulus estimation, which is dependent on season and blueberry variety. We also share our dataset of live blueberry cane deformation, including RGB-D images and measured forces and displacements.